Update README.md
Browse files
README.md
CHANGED
|
@@ -77,6 +77,17 @@ CALM-8B is trained on a **multi-task dataset** covering dialogue state tracking,
|
|
| 77 |
- **Gradient Accumulation Steps:** 1
|
| 78 |
|
| 79 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 80 |
## Usage
|
| 81 |
### 🏗 How to Load the Model using Transformers
|
| 82 |
```python
|
|
|
|
| 77 |
- **Gradient Accumulation Steps:** 1
|
| 78 |
|
| 79 |
---
|
| 80 |
+
## 💡 CALM-IT Dataset
|
| 81 |
+
<img src="table.png" alt="CALM-IT Dataset Statistics" width="800"/>
|
| 82 |
+
|
| 83 |
+
|
| 84 |
+
---
|
| 85 |
+
## 📊 Benchmark Performance
|
| 86 |
+
|
| 87 |
+
<img src="results.png" alt="CALM-IT Dataset Statistics" width="1000"/>
|
| 88 |
+
---
|
| 89 |
+
|
| 90 |
+
|
| 91 |
## Usage
|
| 92 |
### 🏗 How to Load the Model using Transformers
|
| 93 |
```python
|